模倣学習の汎化保証
Generalization Guarantees for Imitation Learning
PAC-Bayes枠組みを用いて模倣学習ポリシーの新環境での期待コストの上界を導出し、条件付きVAEで潜在ポリシー分布を学習後に新環境で汎化境界を最適化する二段階学習法を提案した。
著者: Allen Z. Ren, Sushant Veer, Anirudha Majumdar
分類: cs.RO, cs.LG, cs.SY, eess.SY, math.OC
原文アブストラクト
Control policies from imitation learning can often fail to generalize to novel environments due to imperfect demonstrations or the inability of imitation learning algorithms to accurately infer the expert's policies. In this paper, we present rigorous generalization guarantees for imitation learning by leveraging the Probably Approximately Correct (PAC)-Bayes framework to provide upper bounds on the expected cost of policies in novel environments. We propose a two-stage training method where a latent policy distribution is first embedded with multi-modal expert behavior using a conditional variational autoencoder, and then "fine-tuned" in new training environments to explicitly optimize the generalization bound. We demonstrate strong generalization bounds and their tightness relative to empirical performance in simulation for (i) grasping diverse mugs, (ii) planar pushing with visual feedback, and (iii) vision-based indoor navigation, as well as through hardware experiments for the two manipulation tasks.
